基于递归高斯的指纹增强算法  

A method for fingerprint enhancement based on recursive gaussian filter

作　　者：项灿[1] 游林[2] 

机构地区：[1]海南师范大学数学与统计学院,海南海口571158 [2]杭州电子科技大学通信工程学院,浙江杭州310018

出　　处：《河南科技学院学报》2010年第1期67-70,共4页Journal of Henan Institute of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金(60763009);教育部科学技术研究重点项目(207089);海南省自然科学基金(80528)

摘　　要：通过对二维gabor函数的逐级分解,将gabor函数分解成高斯函数与三角函数的组合,再通过递归的方法实现高斯滤波,从而达到了快速指纹图像增强的目的.实验结果表明,该算法不仅增强效果与gabor增强相当,且在算法速度上较传统方法具有明显优势,同时,一次滤波可以得到两个不同方向的增强结果.By a stepwise decomposition of the two-dimension gabor function,the gabor functions are broken down into the combination of the Gaussian functions and the trigonometric functions,and then the Gaussian filter is implemented in the recursive method.By this method,the fingerprint images can be fast enhanced.Experimental results show that the effect of this method on image enhancement is the same as that of gabor enhancement,and it was superior to the traditional methods in algorithm speed.In addition,two enhancement results in different directions can be obtained by one time filtering.

关 键 词：GABOR滤波 递归高斯 指纹增强 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]